Hi!,
When working with the Gemma 3 models, convert_hf.py uses hf_hub_download, which requires verification.
In a clean environment, once installed the required python packages, the following command
python3 tools/convert_hf.py google/gemma-3-1b-it weights/gemma3-1b/ --precision INT8
gets an error, caught in stdout:
Converting google/gemma-3-1b-it to INT8...
Error: You are trying to access a gated repo.
Make sure to have access to it at https://huggingface.co/google/gemma-3-1b-it.
401 Client Error. (Request ID: Root=1-69082383-3b6d59c846f1b4790a81fac5;44c286de-ddb0-4d22-bb08-a20b0acf0c79)
Cannot access gated repo for url https://huggingface.co/google/gemma-3-1b-it/resolve/main/config.json.
Access to model google/gemma-3-1b-it is restricted. You must have access to it and be authenticated to access it. Please log in.
A quick fix is to export the HF_TOKEN variable. I might do a PR on this, feel free to ignore if it's not relevant.
Hi!,
When working with the Gemma 3 models,
convert_hf.pyuseshf_hub_download, which requires verification.In a clean environment, once installed the required python packages, the following command
gets an error, caught in stdout:
A quick fix is to export the
HF_TOKENvariable. I might do a PR on this, feel free to ignore if it's not relevant.